Ask a vector RAG system about a patient's emphysema care plan and it returns generic advice: respiratory therapy, deep breathing. Give it a graph grounded in that patient's actual history and it knows they smoke, knows they've had an operation, and gives recommendations that reflect it. The information existed in both cases. What changed was whether the system could traverse the relationships connecting it.

Stephen Chin from Neo4j makes the case that retrieval alone is not enough because agents also lose the reasoning behind past decisions. Context graphs capture not just what was retrieved but what decisions were made, why, which policies applied, and what the outcome was, so that precedent is queryable the next time a similar case comes up. The financial services demo shows this concretely: a loan decision that surfaces a prior rejection, related margin trades, and fraud risk patterns, with the graph traversal visible so the human making the final call can actually see what the system is drawing on.

Speaker info:
- https://x.com/steveonjava
- https://linkedin.com/in/steveonjava

AI Engineer

Stephen Chin from Neo4j presents context graphs as a solution to the problem of siloed enterprise data limiting AI agent effectiveness. He explains how combining knowledge graphs with LLMs enables grounded, explainable AI decisions by storing short-term memory, long-term memory, and reasoning traces in a graph structure. A healthcare RAG comparison demonstrates how graph-based retrieval outperforms standard vector search by preserving relational context. A financial services demo shows how context graphs capture decision provenance, fraud patterns, and prior rejections to support auditable loan approval decisions. Neo4j's open-source agent memory package and a free GraphAcademy course on context graphs are highlighted as starting points.

Connecting the Dots with Context Graphs — Stephen Chin, Neo4j